检索结果-内蒙古大学图书馆

36th IEEE/IFIP Network Operations and Management Symposium, NOMS 2023

作者： Tashtarian, Farzad Bentaleb, Abdelhak Amirpour, Hadi Taraghi, Babak Timmerer, Christian Hellwagner, Hermann Zimmermann, Roger Alpen-Adria-Universitat Klagenfurt Christian Doppler Laboratory Athena Austria Concordia University Department of Computer Science and Software Engineering Canada National University of Singapore School of Computing Singapore

ISBN: (纸本)9781665477161

Video content in Live HTTP Adaptive Streaming (HAS) is typically encoded using a pre-defined, fixed set of bitrate-resolution pairs (termed Bitrate Ladder), allowing play-back devices to adapt to changing network conditions using an adaptive bitrate (ABR) algorithm. However, using a fixed one-size-fits-all solution when faced with various content complexities, heterogeneous network conditions, viewer device resolutions and locations, does not result in an overall maximal viewer quality of experience (QoE). Here, we consider these factors and design LALISA, an efficient framework for dynamic bitrate ladder optimization in live HAS. LALISA dynamically changes a live video session's bitrate ladder, allowing improvements in viewer QoE and savings in encoding, storage, and bandwidth costs. LALISA is independent of ABR algorithms and codecs, and is deployed along the path between viewers and the origin server. In particular, it leverages the latest developments in video analytics to collect statistics from video players, content delivery networks and video encoders, to perform bitrate ladder tuning. We evaluate the performance of LALISA against existing solutions in various video streaming scenarios using a trace-driven testbed. Evaluation results demonstrate significant improvements in encoding computation (24.4%) and bandwidth (18.2%) costs with an acceptable QoE. © 2023 IEEE.

关键词： Bandwidth

来源：评论

学校读者我要写书评

暂无评论

Identification of Anomaly Scenes in Videos Using Graph Neural Networks

引用

computers, Materials & Continua 2023年第3期74卷 5417-5430页

作者： Khalid Masood Mahmoud M.Al-Sakhnini Waqas Nawaz Tauqeer Faiz Abdul Salam Mohammad Hamza Kashif Department of Software Engineering Lahore Garrison UniversityLahore54000Pakistan School of Business Skyline University CollegeSharjahUAE Al-Madinah International University–Faculty of Computer and Information Technology Kuala LumpurMalaysia College of Computer and Information Systems Islamic University of MadinahMadinahKingdom of Saudi Arabia School of IT Skyline University CollegeSharjahUAE Faculty of Engineering Computing and Science(FECS)-Swinburne University of TechnologySarawak Department of General Education Skyline University CollegeUniversity City of SharjahUAE Department of Computer Science Lahore Garrison UniversityLahore54000Pakistan

Generally,conventional methods for anomaly detection rely on clustering,proximity,or *** themassive growth in surveillance videos,outliers or anomalies find ingenious ways to obscure themselves in the network and make conventional techniques *** research explores the structure of Graph neural networks(GNNs)that generalize deep learning frameworks to graph-structured *** node in the graph structure is labeled and anomalies,represented by unlabeled nodes,are predicted by performing random walks on the node-based graph *** to their strong learning abilities,GNNs gained popularity in various domains such as natural language processing,social network analytics and *** detection is a challenging task in computer vision but the proposed algorithm using GNNs efficiently performs the identification of *** Graph-based deep learning networks are designed to predict unknown objects and *** our case,they detect unusual objects in the form of malicious *** edges between nodes represent a relationship of nodes among each *** case of anomaly,such as the bike rider in Pedestrians data,the rider node has a negative value for the edge and it is identified as an *** encoding and decoding layers are crucial for determining how statistical measurements affect anomaly identification and for correcting the graph path to the best possible *** show that the proposed framework is a step ahead of the traditional approaches in detecting unusual activities,which shows a huge potential in automatically monitoring surveillance *** autonomous monitoring of CCTV,crime control and damage or destruction by a group of people or crowd can be identified and alarms may be triggered in unusual activities in streets or public *** suggested GNN model improves accuracy by 4%for the Pedestrian 2 dataset and 12%for the Pedestrian 1 dataset compared to a few state-of the-art techniq

关键词： Graph neural network deep learning anomaly detection auto encoders

来源：评论

学校读者我要写书评

暂无评论

AEGAN: Generating imperceptible face synthesis via autoencoder-based generative adversarial network

AEGAN: Generating imperceptible face synthesis via autoencod...

引用

作者： Che, Aolin Yang, Jing-Hua Guo, Cai Dai, Hong-Ning Xie, Haoran Li, Ping Faculty of Innovation Engineering Macau University of Science and Technology China School of Computing and Information Engineering Hanshan Normal University Chaozhou China Department of Computer Science Hong Kong Baptist University Hong Kong Department of Computing and Decision Sciences Lingnan University Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong School of Design The Hong Kong Polytechnic University Hong Kong

Face recognition (FR) systems based on convolutional neural networks have shown excellent performance in human face inference. However, some malicious users may exploit such powerful systems to identify others' face images disclosed by victims' social network accounts, consequently obtaining private information. To address this emerging issue, synthesizing face protection images with visual and protective effects is essential. However, existing face protection methods encounter three critical problems: poor visual effect, limited protective effect, and trade-off between visual and protective effects. To address these challenges, we propose a novel face protection approach in this article. Specifically, we design a generative adversarial network (GAN) framework with an autoencoder (AEGAN) as the generator to synthesize the protection images. It is worth noting that we introduce an interpolation upsampling module in the decoder in order to let the synthesized protection images evade recognition by powerful convolution-based FR systems. Furthermore, we introduce an attention module with a perceptual loss in AEGAN to enhance the visual effects of synthesized images by AEGAN. Extensive experiments have shown that AEGAN not only can maintain the comfortable visual quality of synthesized images but also prevent the recognition of commercial FR systems, including Baidu and iKLYTEK. © 2023 John Wiley & Sons Ltd.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Explainable AI for Intrusion Prevention: A Review of Techniques and Applications 7th

Explainable AI for Intrusion Prevention: A Review of Techniq...

引用

7th International Conference on Information and Communication Technology for Intelligent Systems, ICTIS 2023

作者： Chandre, Pankaj R. Vanarote, Viresh Patil, Rajkumar Mahalle, Parikshit N. Shinde, Gitanjali R. Nimbalkar, Madhukar Barot, Janki Department of Computer Science and Engineering MIT School of Computing MIT ADT University Loni Kalbhor India Department of Information Technology MIT School of Computing MIT ADT University Loni Kalbhor India Department of Artificial Intelligence and Data Science Vishwakarma Institute of Information Technology Kondhawa India Department of Computer Science and Engineering Vishwakarma Institute of Information Technology Kondhawa India Silver Oak University Ahmedabad India

ISBN: (纸本)9789819937578

Intrusion prevention has become a critical concern in today's increasingly complex and interconnected digital systems. Traditional intrusion prevention methods often rely on rule-based approaches that can be inflexible and prone to false positives and false negatives. The emergence of explainable artificial intelligence (AI) techniques has the potential to provide more accurate and interpretable solutions for intrusion prevention. This review paper surveys the current state of the art in explainable AI techniques for intrusion prevention, including their strengths and limitations. We begin by providing an overview of intrusion prevention and the challenges faced by traditional methods. We then explore the different types of explainable AI techniques, such as Local Interpretable Model-Agnostic Explanations (LIME), Shapley Additive Explanations (SHAP), and Integrated Gradients, and their application to intrusion prevention. We also discuss the different types of datasets and evaluation metrics used in explainable AI-based intrusion prevention, including public datasets such as NSL-KDD and UNSW-NB15. Finally, we highlight the future research directions in explainable AI-based intrusion prevention, including the need for larger and more diverse datasets, better evaluation metrics, and more comprehensive explainable AI models. Overall, this review paper provides a comprehensive overview of the state of the art in explainable AI for intrusion prevention, and serves as a valuable resource for researchers and practitioners in the field. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2023.

关键词： Additives

来源：评论

学校读者我要写书评

暂无评论

Towards Dynamic Evolutionary Analysis of ProgrammableWeb for API-Mashup Ecosystem 26

Towards Dynamic Evolutionary Analysis of ProgrammableWeb for...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wang, Yang Xiang, Jiayan Cheng, Hangyu Chen, Wanjun Xiao, Yong Kang, Guosheng Hunan University of Science and Technology School of Computer Science and Engineering Xiangtan China Hunan Provincial Key Lab. for Services Computing and Novel Software Technology Hnust Xiangtan China

ISBN: (纸本)9798350331684

With the wide adoption of Web APIs released on Internet, users tend to reuse them for business requirements or software development. Mashup is a useful technology for composing Web APIs into a new and value-added application. With the increasing number of Web APIs and Mashups, the API-Mashup ecosystem has emerged based on the invocation relationship between Mashups and Web APIs. In this paper, we take ProgrammableWeb, a typical API-Mashup ecosystem, as an example to investigate its dynamic evolutionary analysis. Although there have been some works on the API-Mashup ecosystem, they mainly focus on static analysis, i.e., the static characteristics of the API- Mashup ecosystem on a fixed time point. This paper conducts a comprehensive study on the dynamic evolutionary analysis of the API-Mashup ecosystem with a long time range from 2005 to 2021. First, we conduct a dynamic statistical analysis based on the API-Mashup ecosystem dataset. Next, we construct two cooperation networks, one between Web APIs, and the other between their categories. And the general characteristics of the two cooperation networks are presented. Finally, we investigate the derived cooperation networks from four perspectives: dynamic characteristics, degree distribution, betweenness centrality, and assortative mixing. Meanwhile, the corresponding insights are uncovered. Our work provides a foundation for visualization and understanding of the API-Mashup ecosystem from the timeline. © 2023 IEEE.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Thoracic Surgery Outcome Prediction: Harnessing Machine Learning for Post-Operative Life Expectancy Assessment

Thoracic Surgery Outcome Prediction: Harnessing Machine Lear...

引用

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： Adithya Rajendran S Abhishek Akhbar Sha T Anjali Department of Computer Science and Engineering Amrita School of Computing Amritapuri India

Lung cancer, a complex and formidable disease, frequently necessitates surgical intervention as a pivotal aspect of its treatment. Accurate prediction of post-operative life expectancy holds paramount significance in the realm of clinical decisionmaking and patient counselling This study undertook a rigorous comparison of various machine learning algorithms, encompassing Support Vector Classifier (SVC), Logistic Regression, XGBoost, Random Forest, K-Nearest Neighbors (K-NN), and CatBoost. Using an expansive dataset containing clinical and demographic variables collected from lung cancer patients, the research team rigorously assessed the predictive capabilities of these models. The outcome of the research team analysis unveiled exceptional mean accuracy scores across the models, underscoring their utility in this context. Specifically, SVC, Random Forest, and CatBoost consistently exhibited remarkable mean accuracy rates, each reaching 0.864. Logistic Regression also demonstrated robust performance, achieving a commendable mean accuracy of 0.862, while XGBoost and K-NN delivered competitive mean accuracies of 0.846 and 0.84, respectively. These findings underscore the substantial potential of machine learning in furnishing precise predictions regarding post-operative life expectancy. By doing so, these models empower healthcare professionals to make well-informed treatment decisions, paving the path for the development of personalized treatment strategies and the enhancement of patient care in the management of lung cancer.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fingerspelling Classification for Robot Control 22

Fingerspelling Classification for Robot Control

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： McCready, Kevin Coleman, Sonya Kerr, Dermot Siddique, Nazmul Kerr, Emmett Aloimonos, Yiannis Fermüller, Cornelia School of Computing Engineering and Intelligent Systems Ulster University Londonderry United Kingdom Department of Electronic and Mechanical Engineering Atlantic Technological University Co.Donegal Letterkenny Ireland Institute for Advanced Computer Studies University of Maryland College ParkMD United States

ISBN: (纸本)9798331527471

Improvements to human-robot interaction methods could increase the ease of use of robots in manufacturing environments. Many of these environments are noisy and therefore preclude the use of audio communication between humans or in human-robot interactions. Therefore, this paper proposes using a gesture based communication system for robot control. To that end, the VGG16 and VGG19 convolutional neural network (CNN) structures are used for gesture classification along with 3 datasets of American Sign Language (ASL) fingerspelling images. The model performance is evaluated, and modifications made to their parameters to improve performance, before applying them to robot control tasks. The results show that with parameter tuning, test accuracies of up to, 100% are achievable. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detecting and Characterising Mobile App Metamorphosis in Google Play Store

引用

IEEE Transactions on Mobile computing 2025年

作者： Denipitiyage, D. Silva, B. Gunathilaka, K. Seneviratne, S. Mahanti, A. Seneviratne, A. Chawla, S. University of Sydney School of Computer science Australia University of Moratuwa Department of Computer Science and Engineering Sri Lanka Sydney Australia Qatar Computing Research Institute Qatar

App markets have evolved into highly competitive and dynamic environments for developers. While the traditional app life cycle involves incremental updates for feature enhancements and issue resolution, some apps deviate from this norm by undergoing significant transformations in their use cases or market positioning. We define this previously unstudied phenomenon as 'app metamorphosis.' In this paper, we propose a novel and efficient multi-modal search methodology to identify apps undergoing metamorphosis and apply it to analyse two snapshots of the Google Play Store taken five years apart. Our methodology uncovers various metamorphosis scenarios, including re-births, re-branding, re-purposing, and others, enabling comprehensive characterisation. Although these transformations may register as successful for app developers based on our defined success score metric (e.g., re-branded apps performing approximately 11.3% better than an average top app), we shed light on the concealed security and privacy risks that lurk within, potentially impacting even tech-savvy end-users. © 2002-2012 IEEE.

关键词： Mobile commerce

来源：评论

学校读者我要写书评

暂无评论

Enhancing Driver Safety Using Deep Learning Models

Enhancing Driver Safety Using Deep Learning Models

引用

Global Conference for Advancement in Technology (GCAT)

作者： Ishaan Shokeen Krishnendu M Uday Manju Venugopalan Department of Electronics and Computer Engineering Amrita School of Engineering Bengaluru Amrita Vishwa Vidyapeetham India Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798350376685

ISBN: (纸本)9798350376692

This proposed work emphasizes the critical role of eye movement detection, particularly open and closed eye states, in identifying drowsiness, providing a clear focus on the project's main technological approach and its importance for road safety. The proposed model ensures constant checks on the driver’s safety and provides necessary observations on their behavioral activities. To ensure effective drowsiness detection, different methodologies such as Convolutional Neural Networks (CNN), customized Neural Networks and Recurrent Neural Networks (RNN) were employed for image processing. The CNN model achieved the best results. Two different data sources from Kaggle provided various training images for the model to operate in different scenarios. The proposed model aims to achieve accurate predictions across various case scenarios and to develop the most efficient model for real-time detection and alert systems, ensuring driver safety. Among the models our system gives the best result using CNN reporting an accuracy of 98.53%, and precision, recall and F-score of 98.71%, 98.04% and 98.37% respectively.

关键词： Deep learning Training Recurrent neural networks Accuracy Soft sensors Predictive models Real-time systems Safety Convolutional neural networks Vehicles

来源：评论

学校读者我要写书评

暂无评论

A Survey of Machine Learning Algorithms for Defective Steel Plates Classification 8th

A Survey of Machine Learning Algorithms for Defective Steel ...

引用

8th International Conference on computing, Control and Industrial engineering, CCIE 2024

作者： Gao, Meiyan Wei, Yuanzhou Li, Zhenglin Huang, Bolin Zheng, Changyang Mulati, Aliya College of Engineering and Computing Florida International University Miami United States Department of Computer Science and Engineering Texas A&M University College Station United States Viterbi School of Engineering University of Southern California CaliforniaCA United States School of Engineering Brown University Rhode Island United States Biological Science Florida International University Florida United States

ISBN: (纸本)9789819769339

This paper aims to explore various classification models and data processing techniques for classifying defects on steel plates. The study is based on a dataset of steel plates with seven different types of defects and seeks to identify the most effective combination of machine learning models and data processing techniques for automatic defect recognition. Key methodologies include data augmentation, feature selection, and dimensionality reduction techniques like SMOTE, PCA, and REF. Various models, including Naive Bayes, Logistic Regression, SVM, Decision Trees, Random Forests, and Neural Networks, are evaluated. The results indicate that Hyperparameter Tuning and REF significantly enhance model performance, with Random Forest and Neural Networks achieving the highest accuracy. Random Forest, due to its interpretability and efficiency, is identified as the best model for this classification task. This research lays a foundation for applying machine learning algorithms in industrial defect detection, promising improvements in automation, efficiency, and production quality. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：